most citedExternalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering

5 citations · 6 across the 13 of their papers we have counts for

collaborators
Showing cs.AIShow all

8 papers · 1 filter

cs.AI2026

OSCAR: Optimization-Steered Agentic Planning for Composed Image Retrieval

Teng Wang, Rong Shan, Jianghao Lin +8

Composed image retrieval (CIR) requires complex reasoning over heterogeneous visual and textual constraints. Existing approaches largely fall into two paradigms: unified embedding…

cs.AI2026

Proof-of-Use: Mitigating Tool-Call Hacking in Deep Research Agents

SHengjie Ma, Chenlong Deng, Jiaxin Mao +5

While reinforcement learning (RL) enhances their ability to plan and reason across retrieval steps, we identify a critical failure mode in this setting: Tool-Call Hacking. Unlike e…

cs.AI20261 cited

OThink-R1: Intrinsic Fast/Slow Thinking Mode Switching for Over-Reasoning Mitigation

Shengjia Zhang, Junjie Wu, Jiawei Chen +7

Human cognition operates through two complementary modes: fast intuitive thinking and slow deliberate thinking. Vanilla large language models (LLMs) predominantly follow the fast-t…

cs.AI2025

SAGE: Strategy-Adaptive Generation Engine for Query Rewriting

Teng Wang, Hailei Gong, Changwang Zhang +1

Query rewriting is pivotal for enhancing dense retrieval, yet current methods demand large-scale supervised data or suffer from inefficient reinforcement learning (RL) exploration.…

cs.AI2025

Efficient Agents: Building Effective Agents While Reducing Cost

Ningning Wang, Xavier Hu, Pai Liu +11

The remarkable capabilities of Large Language Model (LLM)-driven agents have enabled sophisticated systems to tackle complex, multi-step tasks, but their escalating costs threaten…

cs.AI2025

OAgents: An Empirical Study of Building Effective Agents

He Zhu, Tianrui Qin, King Zhu +21

Recently, Agentic AI has become an increasingly popular research field. However, we argue that current agent research practices lack standardization and scientific rigor, making it…